Prediction model of oil and gas pipeline corrosion based on grey-linear regression combination

The mechanism of oil and gas pipeline corrosion is complicated, and many factors are ambiguous and interconnected, bringing difficulty to effective prediction of pipeline corrosion rate. In this paper, the grey-linear regression combination model which is capable of dealing with linear and nonlinear factors is put forward for modeling of oil and gas pipeline corrosion. Besides, the BP artificial neural network model is used to correct the residual error of the combination model, in order to further improve the accuracy of prediction. The established model is applied to predict the corrosion rate of some oil and gas pipeline. The results show that in the prediction of oil and gas pipeline corrosion, the grey-linear regression combination model takes both linear factors and nonlinear factors of original data, which is well-performed and can also be applied to predict other complex corrosion systems.